© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7031
    Prev
    Next
    INDEX
    Explanations

    Houston

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on named-entity tokens, in particular uppercase organization and place names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endforeach
    -1.55
     are
    -1.52
     いた
    -1.47
     it
    -1.47
    vetica
    -1.42
     They
    -1.41
    -1.40
     şirket
    -1.32
    izações
    -1.32
    nými
    -1.32
    POSITIVE LOGITS
     Répondre
    1.39
    <bos>
    1.37
    桖
    1.35
    {
    1.31
     {
    1.30
     physi
    1.27
     sains
    1.27
    这样一个
    1.26
    棡
    1.21
     Barcelone
    1.20
    Activations Density 0.026%

    No Known Activations